An Analysis on Gender Classification using Face Images Using DWT, (2D)2PCA and SVM
Classifying gender compared to others and is used in this work. Biometry is the use of physical characteristics like face, fingerprints, iris, etc. of an individual for personal identification. Some of the difficult issues of face biometrics are face detection, face recognition, and face identification. These problems are being researched by the computer vision community for the last few decades. Considering the big population, the authentication process of an individual usually consumes a significant amount of time. One of the attainable solutions is to divide the population into two halves supported gender. This will facilitate to scale back the search area of authentication to nearly half the present information and save substantial quantity of your time. Gender identification through face demands use of sturdy discriminative options and strong classifiers to separate the feminine and male faces with no ambiguity. In this thesis, an investigation has been created on gender classification through facial pictures mistreatment principal part analysis ((2D)2PCA), and support vector machine (SVM). Principle Component Analysis (PCA) could be a spatial property reduction technique, which is used to represent each image as a feature vector in a low dimensional subspace. SVM could be a binary classifier that PCA is the input within the style of options and predicts which of the two attainable categories forms the output. Initially face region is extracted employing a planned complexion segmentation approach. The face region is then subjected to PCA for feature extraction that encodes second order statistics of information. These principal elements area unit fed as input to SVM for classification.
Keywords: Biometrics, face detection, gender classification, (2D)2PCA, SVM
- There are currently no refbacks.